|
Security guardrails for coding agents · agentjail
Offline policy guardrails for coding agents. Block dangerous tool calls, sandbox execution, and audit agent activity. Open source, Apache-2.0.
|
85 % |
|
nd7 — kernel sandbox and secure audit log for AI coding agents
nd7 runs Claude Code and OpenAI Codex CLI inside a sandbox enforced by the operating system and keeps a secure audit log of what the agent did. Open source,...
|
85 % |
|
InstaVM | Production Sandbox for AI Agents
The production control plane for AI agents. Run agents like production servers: isolated, observable, and controlled. Firecracker microVMs with sub-200ms boot.
|
84 % |
|
Home | Scarab Runtime
The hardened execution layer for AI agents. A secure, Linux-native runtime for sandboxing untrusted autonomous code.
|
84 % |
|
WireClaw — Run AI Agents in Isolated Containers
WireClaw is an open-source platform for running AI agents in isolated Linux containers. Each agent gets its own filesystem, identity, and skills. Secure by d...
|
84 % |
|
AgentShield - The Security Audit for Your AI Agents
Open-source security audit for your AI agents: the skills they run, exposed secrets, risky MCP config, and unsafe updates. Runs on your machine.
|
84 % |
|
Mutiqo | Runtime Visibility for AI-Assisted Development
Mutiqo gives AI-assisted development teams local runtime visibility into what coding agents are actually doing on developer machines.
|
84 % |
|
Ambient Authority: enterprise AI security, independently reported
Independent, vendor-neutral reporting on enterprise AI security: prompt injection, agent security, model supply chain, and AI governance.
|
84 % |
|
Evren: The Agent Execution Boundary
Evren is the agent execution boundary. Every privileged action an AI agent takes on a machine is decided against policy, allowed or denied per call, and writ...
|
83 % |
|
Appstrate, the open‑source agent runtime platform · Appstrate
Agentic runtimes that are sovereign, sandboxed, and multi-tenant.
|
83 % |
|
HostKit - AI-Native Server Management
Give your AI agent direct control of a Linux VPS through the Model Context Protocol. No Docker. No Kubernetes. Just systemd, nginx, and PostgreSQL.
|
83 % |
|
Beachead — AI Sandbox Orchestrator
Beachead — Run AI agents in isolated Docker Sandbox microVMs from your desktop. Keep your CLI agent workflow while giving agents access only to the folders a...
|
83 % |
|
Handler.dev — Local Sandboxes + Control Plane for AI Coding Agents
The control plane for accelerated, human-in-the-loop development. Run AI coding agents in isolated sandboxes. Open source and free to self-host.
|
83 % |
|
Ag3ntum - Secure AI Automation, Self-Hosted
Ag3ntum is Claude Code for your servers — secure, multi-user, and under your control. Self-hosted AI agent platform with 6-layer security sandbox, visual fil...
|
83 % |
|
FastClaw
A lightweight AI agent runtime in a single Go binary. Create, manage, and run AI agents — each with its own personality, memory, skills, and tools.
|
83 % |
|
Superserve | Virtual machines for long-horizon agents
Virtual machines for long-horizon agents.
|
83 % |
|
AgentWard — Secure every agent action, from install to runtime
Secure every agent action — from install to runtime. Source-available security platform for AI agents. Scan, enforce, detect, comply.
|
83 % |
|
Agent HQ: a local-first AI agent hub
Agent HQ puts one AI agent on Discord, Telegram, the web and your terminal, keeps your data in a markdown vault on your own machine, and supervises your codi...
|
83 % |
|
@zfuzz/mcp — Security Copilot for AI Coding Agents
The security tool that plugs into your AI coding agent (Cursor, Claude Code, Codex…). It catches vulnerabilities, leaked secrets and dangerous libraries whil...
|
82 % |
|
envpod — Zero-Trust Governance for AI Agents
Kernel-level governance for autonomous AI agents. Every action isolated, auditable, and reversible. OWASP 10/10. One binary, one YAML.
|
82 % |
Detected social media networks